add model

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "lmqg_output/mt5_base_itquad/model_kxlrmt/epoch_5",
+  "_name_or_path": "mt5-base-itquad-qg",
   "add_prefix": false,
   "architectures": [
     "MT5ForConditionalGeneration"
@@ -8,11 +8,13 @@
   "d_kv": 64,
   "d_model": 768,
   "decoder_start_token_id": 0,
+  "dense_act_fn": "gelu_new",
   "dropout_rate": 0.1,
   "eos_token_id": 1,
   "feed_forward_proj": "gated-gelu",
   "initializer_factor": 1.0,
   "is_encoder_decoder": true,
+  "is_gated_act": true,
   "layer_norm_epsilon": 1e-06,
   "model_type": "mt5",
   "num_decoder_layers": 12,
@@ -20,11 +22,12 @@
   "num_layers": 12,
   "output_past": true,
   "pad_token_id": 0,
+  "relative_attention_max_distance": 128,
   "relative_attention_num_buckets": 32,
   "tie_word_embeddings": false,
   "tokenizer_class": "T5Tokenizer",
   "torch_dtype": "float32",
-  "transformers_version": "4.18.0.dev0",
+  "transformers_version": "4.21.2",
   "use_cache": true,
   "vocab_size": 250101
 }

eval/metric.first.answer.paragraph.questions_answers.lmqg_qg_itquad.default.json

@@ -0,0 +1 @@
+{"test": {"QAAlignedF1Score (BERTScore)": 0.8792519554868631, "QAAlignedRecall (BERTScore)": 0.8783621185568647, "QAAlignedPrecision (BERTScore)": 0.8801915746575336, "QAAlignedF1Score (MoverScore)": 0.6190616373017829, "QAAlignedRecall (MoverScore)": 0.6177739809596507, "QAAlignedPrecision (MoverScore)": 0.6204099575403378}, "validation": {"QAAlignedF1Score (BERTScore)": 0.8828671516054232, "QAAlignedRecall (BERTScore)": 0.8827346196356219, "QAAlignedPrecision (BERTScore)": 0.8830127539412927, "QAAlignedF1Score (MoverScore)": 0.6244494707746144, "QAAlignedRecall (MoverScore)": 0.6242945567265075, "QAAlignedPrecision (MoverScore)": 0.6246168644469007}}

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3325465c2d5d1045422fa7710833fdb6e5176fdf5bb656aabfba948510e3453a
-size 2329666125
+oid sha256:a5cfbc317a1618364aa392fcaac6bdad0f35d5dbd167246778291313c1270991
+size 2329630901